{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6781185865402222, "min": 1.6529011726379395, "max": 1.713287115097046, "count": 5 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35280.765625, "min": 4429.6650390625, "max": 36458.75, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 66.51315789473684, "min": 38.57142857142857, "max": 71.1, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20220.0, "min": 1080.0, "max": 20220.0, "count": 5 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1485.9358217837985, "min": 1482.809120536105, "max": 1489.7606724540767, "count": 5 }, "SoccerTwos.Self-play.ELO.sum": { "value": 225862.24491113736, "min": 20856.649414357074, "max": 260974.40521435445, "count": 5 }, "SoccerTwos.Step.mean": { "value": 10579965.0, "min": 10539985.0, "max": 10579965.0, "count": 5 }, "SoccerTwos.Step.sum": { "value": 10579965.0, "min": 10539985.0, "max": 10579965.0, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05356394499540329, "min": -0.08563671261072159, "max": -0.02636147290468216, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.141719818115234, "min": -11.90350341796875, "max": -1.0835962295532227, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05095755308866501, "min": -0.08749444037675858, "max": -0.02714642882347107, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.745548248291016, "min": -12.161726951599121, "max": -1.0566155910491943, "count": 5 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.12187368383533076, "min": -0.2654517966208698, "max": 0.06860555625624126, "count": 5 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -18.524799942970276, "min": -36.8977997303009, "max": 9.879200100898743, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.12187368383533076, "min": -0.2654517966208698, "max": 0.06860555625624126, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -18.524799942970276, "min": -36.8977997303009, "max": 9.879200100898743, "count": 5 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019001084902417156, "min": 0.019001084902417156, "max": 0.019001084902417156, "count": 1 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019001084902417156, "min": 0.019001084902417156, "max": 0.019001084902417156, "count": 1 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09864224642515182, "min": 0.09864224642515182, "max": 0.09864224642515182, "count": 1 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09864224642515182, "min": 0.09864224642515182, "max": 0.09864224642515182, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09997338106234868, "min": 0.09997338106234868, "max": 0.09997338106234868, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09997338106234868, "min": 0.09997338106234868, "max": 0.09997338106234868, "count": 1 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727923256", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\Jason\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1727923307" }, "total": 50.69039320000002, "count": 1, "self": 0.05998539999973218, "children": { "run_training.setup": { "total": 0.06067530000018451, "count": 1, "self": 0.06067530000018451 }, "TrainerController.start_learning": { "total": 50.5697325000001, "count": 1, "self": 0.04038660000287564, "children": { "TrainerController._reset_env": { "total": 4.59870839999985, "count": 2, "self": 4.59870839999985 }, "TrainerController.advance": { "total": 45.81762479999725, "count": 3113, "self": 0.03845090001414064, "children": { "env_step": { "total": 34.328943299995444, "count": 3113, "self": 19.782017400002587, "children": { "SubprocessEnvManager._take_step": { "total": 14.52314989999968, "count": 3113, "self": 0.29699180000625347, "children": { "TorchPolicy.evaluate": { "total": 14.226158099993427, "count": 5677, "self": 14.226158099993427 } } }, "workers": { "total": 0.02377599999317681, "count": 3112, "self": 0.0, "children": { "worker_root": { "total": 46.39741940000613, "count": 3112, "is_parallel": true, "self": 30.55800940002473, "children": { "steps_from_proto": { "total": 0.0017437000001336855, "count": 4, "is_parallel": true, "self": 0.00034060000007229974, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014031000000613858, "count": 16, "is_parallel": true, "self": 0.0014031000000613858 } } }, "UnityEnvironment.step": { "total": 15.837666299981265, "count": 3112, "is_parallel": true, "self": 0.8159926999514937, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5843700999921566, "count": 3112, "is_parallel": true, "self": 0.5843700999921566 }, "communicator.exchange": { "total": 11.985065100010615, "count": 3112, "is_parallel": true, "self": 11.985065100010615 }, "steps_from_proto": { "total": 2.4522384000269994, "count": 6224, "is_parallel": true, "self": 0.4723676000198793, "children": { "_process_rank_one_or_two_observation": { "total": 1.9798708000071201, "count": 24896, "is_parallel": true, "self": 1.9798708000071201 } } } } } } } } } } }, "trainer_advance": { "total": 11.450230599987663, "count": 3112, "self": 0.25559949998614684, "children": { "process_trajectory": { "total": 6.208612800001447, "count": 3112, "self": 6.208612800001447 }, "_update_policy": { "total": 4.986018300000069, "count": 2, "self": 3.089191299999129, "children": { "TorchPOCAOptimizer.update": { "total": 1.8968270000009397, "count": 60, "self": 1.8968270000009397 } } } } } } }, "trainer_threads": { "total": 6.000000212225132e-07, "count": 1, "self": 6.000000212225132e-07 }, "TrainerController._save_models": { "total": 0.11301210000010542, "count": 1, "self": 0.004226500000186206, "children": { "RLTrainer._checkpoint": { "total": 0.10878559999991921, "count": 1, "self": 0.10878559999991921 } } } } } } }